• DocumentCode
    2963463
  • Title

    Neuro-visual control in the Quake II game engine

  • Author

    Parker, Matt ; Bryant, Bobby D.

  • Author_Institution
    Dept. of Comput. Sci. & Eng., Univ. of Nevada, Reno, NV
  • fYear
    2008
  • fDate
    1-8 June 2008
  • Firstpage
    3828
  • Lastpage
    3833
  • Abstract
    The first-person-shooter Quake II is used as a platform to test neuro-visual control and retina input layouts. Agents are trained to shoot a moving enemy as quickly as possible in a visually simple environment, using a neural network controller with evolved weights. Two retina layouts are tested, each with the same number of inputs: first, a graduated density retina which focuses near the center of the screen and blurs outward; second, a uniform retina which focuses evenly across the screen. Results show that the graduated density retina learns more successfully than the uniform retina.
  • Keywords
    computer games; neurocontrollers; Quake II game engine; neural network controller; neuro-visual control; retina input layouts; Artificial intelligence; Cameras; Computational modeling; Engines; Focusing; Humans; Neural networks; Retina; Sensor arrays; Testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on
  • Conference_Location
    Hong Kong
  • ISSN
    1098-7576
  • Print_ISBN
    978-1-4244-1820-6
  • Electronic_ISBN
    1098-7576
  • Type

    conf

  • DOI
    10.1109/IJCNN.2008.4634348
  • Filename
    4634348